initial import and jupyter notebook to check for data issues

notebooks/001_data_cleaning_checks.ipynb

@@ -0,0 +1,45 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8d393e6d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "import os\n",
+    "import sqlite3\n",
+    "import pandas as pd\n",
+    "\n",
+    "# 1. Resolve repository pathing and connect to SQLite\n",
+    "BASE_DIR = os.path.dirname(os.getcwd())\n",
+    "DB_PATH = os.path.join(BASE_DIR, \"data\", \"met_office_weather.db\")\n",
+    "conn = sqlite3.connect(DB_PATH)\n",
+    "\n",
+    "# 2. Extract dataset profile\n",
+    "df = pd.read_sql_query(\"SELECT * FROM historic_weather\", conn)\n",
+    "print(\"--- Dataset Shape ---\")\n",
+    "print(f\"Total Rows: ${df.shape[0]}, Total column: ${df.shape[1]}\\n\")\n",
+    "\n",
+    "print (\"--- Column Data Types & Counts ---\")\n",
+    "print(df.info())\n",
+    "\n",
+    "print(\"\\n--- Missing Values (NaN) Per Feature Column ---\")\n",
+    "print(df.isnull().sum())\n",
+    "\n",
+    "print(\"\\n --- Total Row Logs Collected Per Unique Station ---\")\n",
+    "print(df[\"station_name\"].value_counts())\n",
+    "\n",
+    "conn.close()"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}